Separation of mixed Document Images in Farsi Scanned Documents Using Blind Source Separation

In the field of mixed scanned documents separation, various studies have been carried out to reduce one (or more) unwanted artifacts from the document. Most of the approaches are based on comparison of the front and back sides of the documents. In some cases, it has been proposed to analyze the colored images; however, because of the calculation complexity of the approaches, they are not well applicable in practical applications. Furthermore, none of them are tested on Farsi/Arabic documents. In this paper, an applicable approach to large size images is presented which is based on image block segmentation (mosaicing). The advantages of this approach are less memory usage, combining of the simultaneous and ordinal blind source separation methods in order to increase the algorithm efficiency, reducing calculation complexity of the algorithm into about twenty percents of the basic algorithm, and high stability in noisy images. In noiseless conditions, the average signal to noise ratio of the output images is reached up to 30.26 db. All of these cases have been tested on Farsi official documents. By applying the proposed ideas, considerable accuracy is achieved in the results, at minimum time. In addition, various parameters of the proposed algorithm (e.g. the size of each block, appropriate initial point, and the number of iterations) are optimized.